EP 0177854 B1 19891206 - KEYWORD RECOGNITION SYSTEM USING TEMPLATE-CONCATENATION MODEL
Title (en)
KEYWORD RECOGNITION SYSTEM USING TEMPLATE-CONCATENATION MODEL
Publication
Application
Priority
US 65595884 A 19840928
Abstract (en)
[origin: EP0177854A1] A system employing a method that detects the occurrence of keywords in continuously-spoken speech evaluates both the keyword hypothesis, and the alternative hypothesis that the observed speech is not a keyword. A general language model is used to evaluate the latter hypothesis. Arbitrary utterances of the language, according to this model, are approximated by concatenations of a set of filler templates. The system allows for automatic detection of the occurrence of keywords in unrestricted natural speech. The system can be trained by a particular speaker, or can function independently of the speaker.
IPC 1-7
IPC 8 full level
G10L 15/00 (2013.01); G10L 15/14 (2006.01)
CPC (source: EP)
G10L 15/00 (2013.01); G10L 25/87 (2013.01)
Citation (examination)
- ICASSP 85 PROCEEDINGS, Tampa, Florida, March 26-29, 1985, pages 1233-1236; IEEE, New York, US, A. L. HIGGINS et al.: "Keyword recognition using template concatenation."
- RADIO AND ELECTRONIC ENGINEER, vol. 53, no. 4, April 1983, pages 166-175; IERE Crown Copyright Reserved, London, GB, J.S. BRIDLE et al.: "Continuous connected word recognition using whole word templates"
Designated contracting state (EPC)
AT DE FR GB NL
DOCDB simple family (publication)
EP 0177854 A1 19860416; EP 0177854 B1 19891206; AT E48486 T1 19891215; DE 3574640 D1 19900111; JP H0774960 B2 19950809; JP S61179499 A 19860812
DOCDB simple family (application)
EP 85112261 A 19850927; AT 85112261 T 19850927; DE 3574640 T 19850927; JP 21438185 A 19850927